Arao AI
Back to search results

gemma-4-31B-it · Q6_K

Start a discussion
NVIDIA H100 80GB HBM380GBStrata v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (Q6_K) on NVIDIA H100 80GB HBM3 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

276.83 tok/s

Decode

Decode speed

1,508.76 tok/s

Prefill

Prefill speed

0.3 s

TTFT

Time to first token

67.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · IQ3_XS Decode 338.72 · Prefill 1535.63 ·
  2. vLLM · Q3_K_M Decode 275.73 · Prefill 1508 ·
  3. Strata · Q5_K_S Decode 299.9 · Prefill 1290.71 ·
  4. Strata · Q6_K (current)Decode 276.83 · Prefill 1508.76 ·

Core figures

Decode (avg)
276.83 tok/s
Prefill (avg)
1,508.76 tok/s
TTFT (avg)
0.3 s
VRAM (avg)
67.2 GB
MTP acceptance rate
0.47
TTFB
2.21 GB
Power draw
644.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
Q6_K
Framework
Strata
Version
v0.53
Context length
32768 tokens
Batch size
512
GPU layers
8
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
67.2 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
13.0
Power draw
644.7 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.53 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx

    276.83 tok/s

    Decode

    1,508.76 tok/s

    Prefill

    0.3 s

    TTFT

    67.2 GB

    VRAM

    0.47

    MTP

    644.7 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=55 running model_id=63 at Q6_K